A police drone control platform

Abstract

The present application relates to the field of drones, and specifically to a police drone control platform. It includes: a route planning module, which is used to generate drone flight routes based on geographic information data; a video transmission monitoring module, which is used to display the video data sent back by the drone; a historical trajectory viewing module, which is used to display the historical flight information of the drone, wherein the historical flight information includes the drone number, the pilot's name, the flight time, the flight altitude, the flight distance, and the flight trajectory playback; a data statistics module, which is used to count the total number of flights, the total flight time, and the average flight time within the predetermined time range of the drone, and to display the statistics of the bar chart based on the number of flights within the flight time range; and a drone management module, which is used to perform pre-maintenance management on the drone.

Description

Technical Field

[0001] The present application relates to the field of drones, and specifically to a police drone control platform. Background Art

[0002] With the rapid development of drone technology, police drones have been widely used in the field of public safety, including but not limited to air patrols, emergency rescue, traffic monitoring, reconnaissance and other tasks. In order to ensure that police drones can perform tasks stably and reliably in various complex environments, drones need to have a high degree of reliability and stability.

[0003] However, with the increasing frequency of use, the maintenance and management of drones have become increasingly prominent. Traditional drone maintenance methods often rely on manual inspection and experience judgment, which is difficult to achieve efficient and accurate management. It not only increases maintenance costs, but may also cause drones to be unable to perform tasks normally due to technical failures at critical moments, thus affecting public safety.

[0004] Therefore, we look forward to an intelligent police drone control platform. Summary of the invention

[0005] This application is made in view of the above problems. One purpose of this application is to provide a police drone control platform.

[0006] The embodiment of the present application provides a police drone management and control platform, which includes:

[0007] The route planning module is used to generate the UAV flight route based on geographic information data;

[0008] Image transmission monitoring module, used to display the video data sent back by the drone;

[0009] The historical trajectory viewing module is used to display the historical flight information of the drone, wherein the historical flight information includes the drone number, pilot name, flight time, flight altitude, flight distance, and flight trajectory playback;

[0010] The data statistics module is used to count the total number of flights, total flight time and average flight time within the scheduled time range of the drone, and to display the statistics in a bar chart based on the number of flights within the flight time range;

[0011] UAV management module, used for pre-maintenance management of UAVs;

[0012] Wherein, the drone management module includes:

[0013] A UAV historical flight data acquisition unit, used to acquire historical data of flight state parameters of the analyzed UAV and historical data of motor temperature of the analyzed UAV, wherein the flight state parameters include pitch angle, roll angle, yaw angle, flight speed and flight altitude;

[0014] A flight state parameter temporal feature extraction unit, used to extract temporal correlation features of historical data of the flight state parameters of the analyzed UAV to obtain a full-time domain semantic correlation feature vector between the flight state parameters;

[0015] A motor temperature time series feature extraction unit, used to extract the time series correlation features of the historical data of the motor temperature of the analyzed drone to obtain a motor temperature time series correlation feature vector;

[0016] A feature interaction response analysis unit, used for performing feature interaction response analysis on the full-time domain semantic association feature vector between the flight state parameters and the motor temperature time series association feature vector to obtain a flight state-motor temperature local-global interaction response matrix;

[0017] The pre-maintenance management unit is used to determine whether to perform pre-maintenance on the analyzed UAV based on the flight state-motor temperature local-global interactive response matrix.

[0018] For example, according to the police drone control platform of an embodiment of the present application, the flight state parameter time series feature extraction unit is used to:

[0019] After the historical data of the flight state parameters of the analyzed UAV are arranged into a flight state parameter temporal association matrix according to the time dimension and the parameter sample dimension, the flight state parameter temporal association matrix is ​​input into a flight state parameter temporal association feature extractor based on a converter structure to obtain a full-time domain semantic association feature vector between the flight state parameters.

[0020] For example, according to the police drone control platform of an embodiment of the present application, the motor temperature timing feature extraction unit is used to:

[0021] The historical data of the motor temperature of the analyzed drone is input into a motor temperature timing pattern feature extractor based on a bidirectional LSTM model to obtain the motor temperature timing correlation feature vector.

[0022] For example, according to the police drone control platform of an embodiment of the present application, the feature interaction response analysis unit is used to:

[0023] The full-time semantic association feature vector between the flight state parameters and the motor temperature timing association feature vector are input into a feature local-global interactive response module based on feature decoupling to obtain the flight state-motor temperature local-global interactive response matrix.

[0024] For example, according to the police drone control platform of an embodiment of the present application, the feature interaction response analysis unit includes:

[0025] A feature decoupling subunit, used for performing feature decoupling on the full-time domain semantic association feature vectors between the flight state parameters to obtain a sequence of local association feature vectors between the flight state parameters;

[0026] A nonlinear transformation subunit, used for performing a nonlinear transformation on the motor temperature time series correlation characteristic vector to obtain a nonlinearly transformed motor temperature time series correlation characteristic vector;

[0027] A local interaction subunit is used to calculate the association matrix between the local association feature vectors between the flight state parameters in the sequence of the motor temperature time series association feature vector after the nonlinear transformation and the local association feature vector between the flight state parameters to obtain a sequence of flight state-motor temperature local interaction association matrices;

[0028] a characteristic interaction energy factor calculation subunit, used for calculating the characteristic interaction energy factor of each flight state-motor temperature local interaction correlation matrix in the sequence of the flight state-motor temperature local interaction correlation matrix to obtain a sequence of characteristic interaction energy factors;

[0029] The global interaction fusion subunit is used to fuse the sequence of the flight state-motor temperature local interaction correlation matrix based on the sequence of the characteristic interaction energy factors to obtain the flight state-motor temperature local-global interaction response matrix.

[0030] For example, according to the police drone control platform of an embodiment of the present application, the local interaction association subunit is used to:

[0031] The transposed vector of the motor temperature time series correlation feature vector after the nonlinear transformation is calculated and multiplied by the local correlation feature vector between the flight state parameters to obtain the flight state-motor temperature local interactive correlation matrix.

[0032] For example, according to the police drone control platform of an embodiment of the present application, the characteristic interaction energy factor calculation subunit is used to:

[0033] The kurtosis of the flight state-motor temperature local interaction correlation matrix and the square of the difference between its characteristic mean, the characteristic variance of the flight state-motor temperature local interaction correlation matrix and the weighted sum of the bias terms are calculated, and then the characteristic variance of the flight state-motor temperature local interaction correlation matrix and the bias term are added and divided by the weighted sum to obtain the characteristic interaction energy factor.

[0034] For example, according to the police drone control platform of an embodiment of the present application, the global interactive fusion subunit is used to:

[0035] Inputting the sequence of characteristic interaction energy factors into a Sigmoid function to obtain a sequence of normalized characteristic interaction energy factors;

[0036] The sequence of the normalized characteristic interaction energy factors is used as a sequence of weights, and the position-weighted sum of the sequence of the flight state-motor temperature local interaction correlation matrix is ​​calculated to obtain the flight state-motor temperature local-global interaction response matrix.

[0037] For example, according to the police drone control platform of an embodiment of the present application, the pre-maintenance management unit is used to:

[0038] The flight state-motor temperature local-global interaction response matrix is ​​input into a classifier-based preventive maintenance analyzer to obtain an analysis result, and the analysis result is used to indicate whether to perform pre-maintenance on the analyzed UAV.

[0039] According to the police drone control platform of the embodiment of the present application, it analyzes the historical data of the drone's flight status parameters and the historical data of the motor temperature to identify the potential performance degradation or failure signs of the drone, so as to facilitate preventive maintenance management. In this way, not only can the service life of the drone be extended, but also mission failure or safety risks caused by drone failure can be avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application are briefly introduced below. Obviously, the drawings described below only relate to some embodiments of the present application, and are not intended to limit the present application.

[0041] Figure 1 A schematic diagram of the structure of a police drone control platform in an embodiment of the present application is shown;

[0042] Figure 2 A schematic diagram of the structure of a drone management module of a police drone control platform in an embodiment of the present application is shown;

[0043] Figure 3A flowchart of a police drone control method in an embodiment of the present application is shown; and

[0044] Figure 4 The application scenario diagram of the police drone control platform in the embodiment of the present application is shown. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present application.

[0046] The terms used in this specification are those common terms currently widely used in the art in consideration of the functions of the present application, but these terms may vary according to the intentions of those skilled in the art, precedents, or new technologies in the art. In addition, specific terms may be selected, and in this case, their detailed meanings will be described in the detailed description of the present application. Therefore, the terms used in the specification should not be understood as simple names, but rather as a general description based on the meaning of the terms and the present application.

[0047] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0048] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. At the same time, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0049] In addition, the application architecture diagram in the embodiment of the present application is intended to more clearly illustrate the technical solution in the embodiment of the present application, and does not constitute a limitation on the technical solution provided in the embodiment of the present application. Of course, for other application architectures and business applications, the technical solution provided in the embodiment of the present application is also applicable to similar problems.

[0050] The following is a non-restrictive description of the police drone control platform provided according to at least one embodiment of the present application through several examples or embodiments. As described below, different features in these specific examples or embodiments can be combined with each other without conflicting with each other to obtain new examples or embodiments, and these new examples or embodiments also fall within the scope of protection of this application.

[0051] This application proposes a police drone control platform. Figure 1 The schematic diagram of the structure of the police drone control platform 800 in the embodiment of the present application is shown. The police drone control platform 800 includes: a route planning module 810, which is used to generate a drone flight route based on geographic information data; a video transmission monitoring module 820, which is used to display the video data sent back by the drone; a historical trajectory viewing module 830, which is used to display the historical flight information of the drone, wherein the historical flight information includes the drone number, the pilot name, the flight time, the flight altitude, the flight distance, and the flight trajectory playback; a data statistics module 840, which is used to count the total number of flights, the total flight time, and the average flight time of the drone within a predetermined time range, and to display the bar chart statistics based on the number of flights within the flight time range; and a drone management module 850, which is used to perform pre-maintenance management on the drone.

[0052] Specifically, the route planning module can automatically plan routes based on data such as terrain, no-fly zones, restricted zones, civil aviation clear zones, and custom no-fly zones. It can display the relative height of the flight route to the ground, and supports planning of flight routes based on waypoints. At the same time, drones can be specified to perform specific actions at different waypoints, such as taking pictures, recording videos, adjusting the gimbal angle, etc. The image transmission monitoring module can realize the video streaming transmission of any drone that supports the RTMP protocol, and can view the real-time transmitted video to assist the command center personnel in understanding the real-time images taken by the drone; and supports the layout management of video display, and the standard modes are: four-grid display, six-grid display, and nine-grid display. The historical trajectory viewing module supports the display of drone number, pilot name, flight duration, flight altitude, flight distance, and flight trajectory playback. Among them, the flight trajectory playback supports the display of the location on the map, as well as the latitude and longitude, speed and altitude information of the corresponding time point, and supports multiple-speed playback. The data statistics module is used to count the total number of flights, total flight time and average flight time within a predetermined time range of the drone, and to display the statistics in a bar chart based on the number of flights within the flight time range, such as "the number of flights within the flight time range of 0-5 minutes is 2 times", "the number of flights within the flight time range of 5-10 minutes is 3 times", etc. It also supports flight log statistical analysis based on specific teams or members.

[0053] In terms of the maintenance and management of drones, traditional drone maintenance methods often rely on manual inspection and empirical judgment, which makes it difficult to achieve efficient and accurate management. This not only increases maintenance costs, but may also cause drones to be unable to perform tasks normally due to technical failures at critical moments, thereby affecting public safety. In response to this problem, the technical concept of this application is to use artificial intelligence technology based on deep learning to perform data analysis on the flight status parameters and motor temperatures of drones in historical periods, and to respectively mine the full-time domain semantic association features of various flight status parameters of drones, as well as the time series dynamic change features of motor temperatures, and then based on the associated response relationship between flight status and motor temperature, intelligently identify whether the drone needs pre-maintenance. In this way, efficient and accurate management of police drones can be achieved, maintenance costs can be reduced, and the reliability of drone mission execution can be improved.

[0054] Accordingly, if Figure 2 As shown, the UAV management module 850 includes: a UAV historical flight data acquisition unit 851, which is used to acquire the historical data of the flight state parameters of the analyzed UAV and the historical data of the motor temperature of the analyzed UAV, wherein the flight state parameters include pitch angle, roll angle, yaw angle, flight speed and flight altitude; a flight state parameter time series feature extraction unit 852, which is used to extract the time series correlation features of the historical data of the flight state parameters of the analyzed UAV to obtain the full-time domain semantic correlation feature vector between the flight state parameters; a motor temperature time series feature extraction unit 853, which is used to extract the time series correlation features of the historical data of the motor temperature of the analyzed UAV to obtain the motor temperature time series correlation feature vector; a feature interaction response analysis unit 854, which is used to perform feature interaction response analysis on the full-time domain semantic correlation feature vector between the flight state parameters and the motor temperature time series correlation feature vector to obtain a flight state-motor temperature local-global interaction response matrix; a pre-maintenance management unit 855, which is used to determine whether to perform pre-maintenance on the analyzed UAV based on the flight state-motor temperature local-global interaction response matrix.

[0055] Specifically, in the technical solution of the present application, first, the historical data of the flight state parameters of the analyzed UAV and the historical data of the motor temperature of the analyzed UAV are obtained, wherein the flight state parameters include pitch angle, roll angle, yaw angle, flight speed and flight altitude. It should be understood that the flight state parameters such as pitch angle, roll angle, yaw angle, flight speed and flight altitude can fully display the dynamic characteristics and operating state of the UAV during flight. At the same time, as a key component in the UAV, the working state of the motor directly affects the overall performance of the UAV. The motor temperature, as an important indicator of the working state of the motor, can reflect the operating efficiency and health state of the motor. Based on this, in the technical solution of the present application, by analyzing the historical data of the flight state parameters of the UAV and the historical data of the motor temperature, the potential performance degradation or fault signs of the UAV can be identified, so as to facilitate preventive maintenance management. In this way, not only can the service life of the UAV be extended, but also the mission failure or safety risk caused by the failure of the UAV can be avoided.

[0056] Next, considering that the state parameters of the drone change continuously over time during flight, and there is a correlation between different parameters. Therefore, in order to mine the temporal correlation change relationship of multiple flight state parameters in the global time domain, in the technical solution of the present application, the historical data of the flight state parameters of the analyzed drone are first arranged into a flight state parameter temporal correlation matrix according to the time dimension and the parameter sample dimension, for example, each row represents a specific time point, and the column represents a different parameter type, so as to maintain the temporal sequence of the parameters and the correlation between the parameters. Then, the flight state parameter temporal correlation matrix is ​​processed by a flight state parameter temporal correlation feature extractor based on a converter structure, and mapped into a query vector, a key vector and a value vector. The correlation weight distribution between the query vector, the key vector and the value vector is calculated through the self-attention mechanism of the converter structure to capture the complex correlation between different flight state parameters, reveal the dynamic characteristics of the drone in different flight stages, and generate a full-time domain semantic correlation feature vector between the flight state parameters, thereby providing strong data support for subsequent pre-maintenance decisions.

[0057] Correspondingly, the flight state parameter temporal feature extraction unit 852 is used to: arrange the historical data of the flight state parameters of the analyzed UAV into a flight state parameter temporal association matrix according to the time dimension and the parameter sample dimension, and then input the flight state parameter temporal association matrix into a flight state parameter temporal association feature extractor based on a converter structure to obtain a full-time domain semantic association feature vector between the flight state parameters.

[0058] At the same time, in order to capture the temporal dynamic change characteristics of the drone motor temperature, this application uses a motor temperature timing pattern feature extractor based on a bidirectional LSTM model to perform time encoding on the historical data of the motor temperature of the analyzed drone, and utilizes the bidirectional memory capability of the bidirectional LSTM model while considering the forward and backward dependencies of the motor temperature in the time series to capture the timing change pattern of the motor temperature, thereby effectively mining the timing fluctuation information of the motor temperature and generating a motor temperature timing correlation feature vector.

[0059] Correspondingly, the motor temperature timing feature extraction unit 853 is used to: input the historical data of the motor temperature of the analyzed drone into the motor temperature timing pattern feature extractor based on the bidirectional LSTM model to obtain the motor temperature timing associated feature vector.

[0060] Considering that in practical applications, there are usually certain interactions and correlations between flight state parameters and motor temperature. For example, in certain high-intensity flight modes, the motor temperature may rise. Since this correlation and action intensity have important indicative significance for the performance of the UAV, in the technical solution of the present application, a comprehensive evaluation of the performance of the UAV is performed by further analyzing the correlation response relationship between the flight state parameters and the motor temperature. Based on this, the present application introduces a feature local-global interactive response module based on feature decoupling to process the full-time domain semantic association feature vector between the flight state parameters and the motor temperature timing association feature vector. Specifically, the module first decomposes the full-time domain semantic association feature vector between the flight state parameters into a sequence of local association feature vectors between the flight state parameters through a decoupling operation to reveal different dimensions or aspects within it and enhance the model's ability to capture local features. At the same time, the motor temperature timing association feature vector is nonlinearly transformed in the hope of introducing more complex feature interactions and enhancing the model's expressive power. Next, the correlation matrix between the motor temperature time series correlation feature vector after nonlinear transformation and the local correlation feature vector between each flight state parameter after decoupling is calculated to capture the interaction between feature vectors, reveal the correlation and information flow between features, and thus form a sequence of local interaction correlation matrices. Then, the characteristic interaction energy factors of each local interaction correlation matrix are further calculated to reveal the strength and importance of the interaction between feature vectors. The characteristic interaction energy factor sequence is normalized by the Sigmoid function so that its value range falls within the interval (0,1), and it is converted into an attention weight to perform weighted summation on the local interaction correlation matrix sequence, thereby strengthening the most critical feature interaction and performing global integration of local interaction information to obtain the flight state-motor temperature local-global interaction response matrix. In this way, a fine-grained correlation response representation between flight state parameters and motor temperature is effectively provided, providing a more comprehensive and accurate basis for the pre-maintenance decision of UAVs.

[0061] Correspondingly, the feature interaction response analysis unit 854 is used to: input the full-time domain semantic association feature vector between the flight state parameters and the motor temperature timing association feature vector into the feature local-global interaction response module based on feature decoupling to obtain the flight state-motor temperature local-global interaction response matrix.

[0062] Specifically, the feature interaction response analysis unit 854 includes: a feature decoupling subunit, which is used to perform feature decoupling on the full-time domain semantic association feature vector between the flight state parameters to obtain a sequence of local association feature vectors between the flight state parameters; a nonlinear transformation subunit, which is used to perform nonlinear transformation on the motor temperature time series association feature vector to obtain the motor temperature time series association feature vector after nonlinear transformation; a local interaction association subunit, which is used to calculate the association matrix between the motor temperature time series association feature vector after nonlinear transformation and each local association feature vector between the flight state parameters in the sequence of local association feature vectors between the flight state parameters to obtain a sequence of flight state-motor temperature local interaction association matrices; a feature interaction energy factor calculation subunit, which is used to calculate the feature interaction energy factor of each flight state-motor temperature local interaction association matrix in the sequence of flight state-motor temperature local interaction association matrices to obtain a sequence of feature interaction energy factors; a global interaction fusion subunit, which is used to fuse the sequence of flight state-motor temperature local interaction association matrices based on the sequence of feature interaction energy factors to obtain the flight state-motor temperature local-global interaction response matrix.

[0063] Wherein, the local interaction correlation subunit is used to: calculate the transposed vector of the motor temperature time series correlation feature vector after the nonlinear transformation and multiply it by the local correlation feature vector between the flight state parameters to obtain the flight state-motor temperature local interaction correlation matrix.

[0064] Among them, the characteristic interaction energy factor calculation subunit is used to: calculate the kurtosis of the flight state-motor temperature local interaction correlation matrix and the square of the difference between its characteristic mean, the characteristic variance of the flight state-motor temperature local interaction correlation matrix and the weighted sum of the bias terms, and then add the characteristic variance of the flight state-motor temperature local interaction correlation matrix and the bias term and divide the sum by the weighted sum to obtain the characteristic interaction energy factor.

[0065] Among them, the global interaction fusion subunit is used to: input the sequence of the characteristic interaction energy factors into the Sigmoid function to obtain a sequence of normalized characteristic interaction energy factors; use the sequence of normalized characteristic interaction energy factors as a sequence of weights, calculate the position-weighted sum of the sequence of the flight state-motor temperature local interaction correlation matrix to obtain the flight state-motor temperature local-global interaction response matrix.

[0066] In a specific example, the feature interaction response analysis unit 854 is used to: process the full-time semantic association feature vector between the flight state parameters and the motor temperature timing association feature vector using the following interaction response formula to obtain the flight state-motor temperature local-global interaction response matrix; wherein the interaction response formula is:

[0067]

[0068]

[0069]

[0070]

[0071]

[0072]

[0073]

[0074] in, is the motor temperature timing correlation feature vector, is the full-time domain semantic association feature vector between the flight state parameters, is the weight matrix, is the bias vector, is the motor temperature time series correlation feature vector after nonlinear transformation, Indicates decoupling processing, , , , respectively represent the first, second, and third in the sequence of local correlation feature vectors between the flight state parameters. and The local correlation feature vector between flight state parameters, represents the transpose of a vector, represents the matrix multiplication operation, Indicates The flight state-motor temperature local interaction correlation matrix, that is, the motor temperature time series correlation feature vector and the The correlation matrix between the local correlation eigenvectors between the flight state parameters, Indicates the The characteristic interaction energy factor of the flight state-motor temperature local interaction correlation matrix, , and Respectively represent the The kurtosis, eigenmean and eigenvariance of the local interaction matrix of flight state-motor temperature, is the bias term, Indicates the The fourth-order central moment of the flight state-motor temperature local interaction matrix, that is, The expected value of the fourth power of the difference between each eigenvalue and its eigenmean in the local interaction matrix of flight state-motor temperature, represents the sigmoid activation function, Indicates Normalized feature interaction energy factor, Represents the flight state-motor temperature local-global interaction response matrix.

[0075] Furthermore, the flight state-motor temperature local-global interactive response matrix is ​​input into a classifier-based preventive maintenance analyzer to obtain an analysis result, and the analysis result is used to indicate whether to perform pre-maintenance on the analyzed UAV.

[0076] Accordingly, the preventive maintenance management unit 855 is used to: input the flight status-motor temperature local-global interaction response matrix into a classifier-based preventive maintenance analyzer to obtain an analysis result, and the analysis result is used to indicate whether to perform preventive maintenance on the analyzed UAV.

[0077] It should be understood that the role of the classifier is to use the given categories and known training data to learn classification rules and classifiers, and then classify (or predict) unknown data. Logistic regression, SVM, etc. are often used to solve binary classification problems. For multi-class classification problems, logistic regression or SVM can also be used, but multiple binary classifications are required to form a multi-classification, but this is prone to errors and inefficient. Commonly used multi-classification methods include the Softmax classification function.

[0078] In a preferred example, the preventive maintenance management unit 855 includes: an optimization subunit, used to optimize the flight state-motor temperature local-global interaction response matrix to obtain an optimized flight state-motor temperature local-global interaction response matrix; a classification subunit, used to input the optimized flight state-motor temperature local-global interaction response matrix into the classifier-based preventive maintenance analyzer to obtain the analysis result.

[0079] Wherein, the optimization subunit is used to: calculate the sum of the absolute values ​​of each eigenvalue of the flight state-motor temperature local-global interaction response matrix to obtain the first flight state-motor temperature local-global interaction response and modulation value, and calculate the square root of the sum of the squares of each eigenvalue of the flight state-motor temperature local-global interaction response matrix to obtain the second flight state-motor temperature local-global interaction response and modulation value; after point subtraction of the flight state-motor temperature local-global interaction response matrix and the second flight state-motor temperature local-global interaction response and modulation value, respectively perform point multiplication with the number of eigenvalues ​​of the flight state-motor temperature local-global interaction response matrix and the inverse of the first flight state-motor temperature local-global interaction response and modulation value, and take the inverse of each eigenvalue to obtain the first flight state -motor temperature local-global interaction response phase conversion matrix; after point subtraction of the flight state-motor temperature local-global interaction response matrix and the first flight state-motor temperature local-global interaction response and modulation value, respectively perform point multiplication with the square root of the number of eigenvalues ​​of the flight state-motor temperature local-global interaction response matrix and the inverse of the second flight state-motor temperature local-global interaction response and modulation value, and take the inverse of each eigenvalue to obtain the second flight state-motor temperature local-global interaction response phase conversion matrix; point subtraction of the first flight state-motor temperature local-global interaction response phase conversion matrix by the point product vector of the second flight state-motor temperature local-global interaction response phase conversion matrix and the weighted hyperparameter to obtain the optimized flight state-motor temperature local-global interaction response matrix.

[0080] Here, in one example, the optimization subunit is used to optimize the flight state-motor temperature local-global interaction response matrix using the following optimization formula to obtain the optimized flight state-motor temperature local-global interaction response matrix; wherein the optimization formula is:

[0081]

[0082]

[0083]

[0084]

[0085]

[0086]

[0087]

[0088] in, represents the flight state-motor temperature local-global interaction response matrix, The flight state-motor temperature local-global interaction response matrix is ​​represented by eigenvalues, The value of is the number of eigenvalues ​​in the flight state-motor temperature local-global interaction response matrix, and represent the width and height of the flight state-motor temperature local-global interaction response matrix, respectively, represents the absolute value symbol, is the first flight state-motor temperature local-global interaction response and modulation value, The second flight state-motor temperature local-global interaction response and modulation value, represents dot product, Indicates point reduction, It means to calculate the inverse of each eigenvalue in the matrix. represents the first flight state-motor temperature local-global interaction response phase conversion matrix, represents the second flight state-motor temperature local-global interaction response phase conversion matrix, is the weighted hyperparameter, is the optimized flight state-motor temperature local-global interaction response matrix.

[0089] That is, considering that the full-time domain semantic association feature vector between the flight state parameters and the motor temperature timing association feature vector respectively represent the full-time domain contextual semantic association features between the flight state parameters based on the converter structure and the long-range-short-range timing association features of the motor temperature, when they are passed through the feature local-global interactive response module based on feature decoupling, the timing association feature distribution pattern based on the source timing distribution will also have local-global timing-decoding prediction interactive response differences. Therefore, it is expected to improve the detailed interactive response semantic aggregation expression effect of the flight state-motor temperature local-global interactive response matrix based on the association pattern representation difference.

[0090] Therefore, in the preferred example, the difference of the different and modulated representations of the eigenvalues ​​of the flight state-motor temperature local-global interaction response matrix relative to the overall feature set of the flight state-motor temperature local-global interaction response matrix is ​​used as semantic change intensity information, and a phase-like transformation corresponding to the position-based intensity modulation is performed through different and modulated representations, so that the aggregation enhancement of semantic change phase perception can enhance the axial aggregation receptive field along the feature aggregation direction by performing a spatial translation operation based on alternating stacking under the set scale balance of the flight state-motor temperature local-global interaction response matrix, thereby improving the perception effect of the aggregated semantics of the flight state-motor temperature local-global interaction response matrix on the detailed semantic changes, so as to improve the expression effect of the flight state-motor temperature local-global interaction response matrix, and improve the accuracy of the analysis result obtained by inputting it into the classifier-based preventive maintenance analyzer.

[0091] Based on the above embodiments, see Figure 3 As shown in FIG. 1 , it is a flow chart of a method for controlling a police drone in an embodiment of the present application. Figure 3 As shown, according to the police drone control method of the embodiment of the present application, the steps include: S510, generating a drone flight route based on geographic information data; S520, displaying the video data sent back by the drone; S530, displaying the historical flight information of the drone, wherein the historical flight information includes the drone number, pilot name, flight time, flight altitude, flight distance, and flight trajectory playback; S540, counting the total number of flights, total flight time, and average flight time within a predetermined time range of the drone, and performing a bar chart statistical display based on the number of flights within the flight time range; S550, performing pre-maintenance management on the drone.

[0092] Among them, in step S550, the UAV is pre-maintenance managed, including: obtaining historical data of flight state parameters of the analyzed UAV and historical data of the motor temperature of the analyzed UAV, wherein the flight state parameters include pitch angle, roll angle, yaw angle, flight speed and flight altitude; extracting the time series correlation features of the historical data of the flight state parameters of the analyzed UAV to obtain a full-time domain semantic correlation feature vector between flight state parameters; extracting the time series correlation features of the historical data of the motor temperature of the analyzed UAV to obtain a motor temperature time series correlation feature vector; performing feature interaction response analysis on the full-time domain semantic correlation feature vector between the flight state parameters and the motor temperature time series correlation feature vector to obtain a flight state-motor temperature local-global interaction response matrix; based on the flight state-motor temperature local-global interaction response matrix, determining whether to perform pre-maintenance on the analyzed UAV.

[0093] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned police drone control method have been referred to above. Figure 1 to Figure 2 It has been introduced in detail in the description of the police drone control platform 800, and therefore, its repeated description will be omitted.

[0094] Figure 4 FIG. 1 is an application scenario diagram of the police drone control platform according to an embodiment of the present application. Figure 4 As shown, in this application scenario, first, the historical data of the flight status parameters of the analyzed UAV are obtained (for example, Figure 4 D1 as shown in the figure) and the historical data of the motor temperature of the analyzed drone (e.g., Figure 4 Then, the historical data of the flight state parameters of the analyzed drone and the historical data of the motor temperature of the analyzed drone are input into a server (for example, Figure 4 In S) as shown in , the server can use the police drone management and control algorithm to process the historical data of the flight status parameters of the analyzed drone and the historical data of the motor temperature of the analyzed drone to obtain an analysis result indicating whether to perform pre-maintenance on the analyzed drone.

[0095] It should be understood that the online drone can be used to view the real-time location and detailed information of all police drones in flight, and the real-time location of the drone can be dynamically displayed on the map, and the returned video information can be viewed. For the gimbal mounted on the drone, the gimbal direction, zoom, and whether to track the target can be controlled on the web end.

[0096] Real-time monitoring can realize snapshot, and the permissions include the ability to switch lenses or record videos, so that the captured pictures or videos can be saved to the local computer for convenient viewing on the local computer; scanning the QR code can realize real-time viewing on any mobile phone, and clicking the link can realize real-time viewing on any computer.

[0097] Based on the above embodiments, another exemplary embodiment of an electronic device is also provided in the embodiments of the present application. In some possible implementations, the electronic device in the embodiments of the present application may include a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor can implement the steps of the police drone control method in the above embodiments when executing the program.

[0098] The embodiment of the present application also provides a computer-readable storage medium, on which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the police drone control method according to the embodiment of the present application described with reference to the above figures can be executed. The computer-readable storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory may, for example, include a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may, for example, include a read-only memory (ROM), a hard disk, a flash memory, etc.

[0099] The embodiments of the present application also provide a computer program product or a computer program, which includes computer executable instructions, and the computer executable instructions are stored in a computer readable storage medium. The processor of the computer device reads the computer executable instructions from the computer readable storage medium, and the processor executes the computer executable instructions, so that the computer device executes the police drone control method according to the embodiments of the present application.

[0100] Those skilled in the art will appreciate that the contents disclosed in this application may be subject to various variations and improvements. For example, the various devices or components described above may be implemented by hardware, or by software, firmware, or a combination of some or all of the three.

[0101] In addition, although the present application makes various references to certain units in the system according to embodiments of the present application, any number of different units can be used and run on the client and / or server. The units are only illustrative, and different aspects of the system and method can use different units.

[0102] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each module / unit in the above embodiment can be implemented in the form of hardware or in the form of software function modules. The present application is not limited to any particular form of combination of hardware and software.

[0103] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined as such herein.

[0104] The above is an explanation of the present application and should not be considered as limiting thereof. Although several exemplary embodiments of the present application have been described, those skilled in the art will readily appreciate that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present application.

Claims

1. A police drone control platform, characterized in that: include: The route planning module is used to generate the UAV flight route based on geographic information data; Image transmission monitoring module, used to display the video data sent back by the drone; The historical trajectory viewing module is used to display the historical flight information of the drone, wherein the historical flight information includes the drone number, pilot name, flight time, flight altitude, flight distance, and flight trajectory playback; The data statistics module is used to count the total number of flights, total flight time and average flight time within the scheduled time range of the drone, and to display the statistics in a bar chart based on the number of flights within the flight time range; UAV management module, used for pre-maintenance management of UAVs; Wherein, the drone management module includes: A UAV historical flight data acquisition unit, used to acquire historical data of flight state parameters of the analyzed UAV and historical data of motor temperature of the analyzed UAV, wherein the flight state parameters include pitch angle, roll angle, yaw angle, flight speed and flight altitude; A flight state parameter temporal feature extraction unit, used to extract temporal correlation features of historical data of the flight state parameters of the analyzed UAV to obtain a full-time domain semantic correlation feature vector between the flight state parameters; A motor temperature time series feature extraction unit, used to extract the time series correlation features of the historical data of the motor temperature of the analyzed drone to obtain a motor temperature time series correlation feature vector; A feature interaction response analysis unit, used for performing feature interaction response analysis on the full-time domain semantic association feature vector between the flight state parameters and the motor temperature time series association feature vector to obtain a flight state-motor temperature local-global interaction response matrix; A pre-maintenance management unit, used to determine whether to perform pre-maintenance on the analyzed UAV based on the flight state-motor temperature local-global interactive response matrix; The flight state parameter time series feature extraction unit is used to: After the historical data of the flight state parameters of the analyzed UAV are arranged into a flight state parameter temporal association matrix according to the time dimension and the parameter sample dimension, the flight state parameter temporal association matrix is ​​input into a flight state parameter temporal association feature extractor based on a converter structure to obtain a full-time domain semantic association feature vector between the flight state parameters.

2. The police drone control platform according to claim 1 is characterized in that: The motor temperature timing feature extraction unit is used to: The historical data of the motor temperature of the analyzed drone is input into a motor temperature timing pattern feature extractor based on a bidirectional LSTM model to obtain the motor temperature timing correlation feature vector.

3. The police drone control platform according to claim 2 is characterized in that: The feature interaction response analysis unit is used to: The full-time semantic association feature vector between the flight state parameters and the motor temperature timing association feature vector are input into a feature local-global interactive response module based on feature decoupling to obtain the flight state-motor temperature local-global interactive response matrix.

4. The police drone control platform according to claim 3 is characterized in that: The feature interaction response analysis unit comprises: A feature decoupling subunit, used for performing feature decoupling on the full-time domain semantic association feature vectors between the flight state parameters to obtain a sequence of local association feature vectors between the flight state parameters; A nonlinear transformation subunit, used for performing a nonlinear transformation on the motor temperature time series correlation characteristic vector to obtain a nonlinearly transformed motor temperature time series correlation characteristic vector; A local interaction subunit is used to calculate the association matrix between the local association feature vectors between the flight state parameters in the sequence of the motor temperature time series association feature vector after the nonlinear transformation and the local association feature vector between the flight state parameters to obtain a sequence of flight state-motor temperature local interaction association matrices; a characteristic interaction energy factor calculation subunit, used for calculating the characteristic interaction energy factor of each flight state-motor temperature local interaction correlation matrix in the sequence of the flight state-motor temperature local interaction correlation matrix to obtain a sequence of characteristic interaction energy factors; The global interaction fusion subunit is used to fuse the sequence of the flight state-motor temperature local interaction correlation matrix based on the sequence of the characteristic interaction energy factors to obtain the flight state-motor temperature local-global interaction response matrix.

5. The police drone control platform according to claim 4 is characterized in that: The local interaction subunit is used for: The transposed vector of the motor temperature time series correlation feature vector after the nonlinear transformation is calculated and multiplied by the local correlation feature vector between the flight state parameters to obtain the flight state-motor temperature local interactive correlation matrix.

6. The police drone control platform according to claim 5 is characterized in that: The characteristic interaction energy factor calculation subunit is used to: The kurtosis of the flight state-motor temperature local interaction correlation matrix and the square of the difference between its characteristic mean, the characteristic variance of the flight state-motor temperature local interaction correlation matrix and the weighted sum of the bias terms are calculated, and then the characteristic variance of the flight state-motor temperature local interaction correlation matrix and the bias term are added and divided by the weighted sum to obtain the characteristic interaction energy factor.

7. The police drone control platform according to claim 6, characterized in that: The global interaction fusion subunit is used for: Inputting the sequence of characteristic interaction energy factors into a Sigmoid function to obtain a sequence of normalized characteristic interaction energy factors; The sequence of the normalized characteristic interaction energy factors is used as a sequence of weights, and the position-weighted sum of the sequence of the flight state-motor temperature local interaction correlation matrix is ​​calculated to obtain the flight state-motor temperature local-global interaction response matrix.

8. The police drone control platform according to claim 7, characterized in that: The pre-maintenance management unit is used to: The flight state-motor temperature local-global interaction response matrix is ​​input into a classifier-based preventive maintenance analyzer to obtain an analysis result, and the analysis result is used to indicate whether to perform pre-maintenance on the analyzed UAV.

Images